Installation

Installation from source

If your machine has a GPU with appropriate drivers installed, it should be automatically detected, and the appropriate version of PyTorch with CUDA support should automatically be downloaded as a CellCap dependency.

We recommend installing CellCap in its own conda environment. This allows for easier installation and prevents conflicts with any other python packages you may have installed.

Create a conda environment and activate it:

$ conda create -n cellcap python=3.9
$ conda activate cellcap

Install pytorch via these instructions:

(cellcap) $ pip install torch

and ensure that your installation is appropriate for your hardware (i.e. that the relevant CUDA drivers get installed and that torch.cuda.is_available() returns True if you have a GPU available.

Clone this repository and install CellCap (in editable -e mode):

(cellcap) $ git clone https://github.com/broadinstitute/CellCap.git
(cellcap) $ pip install -e CellCap

Via pip (coming soon)

Python packages can be conveniently installed from the Python Package Index (PyPI) using pip install. CellCap is available on PyPI and can be installed via

$ pip install cellcap

$ conda create -n cellcap python=3.9
$ conda activate cellcap
(cellcap) $ pip install cellcap